Epi2melabs pychopper

CHANGELOG.md

@@ -4,9 +4,10 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
-## [unreleased]
+## [v0.1.3]
 ### Changed
 - Better help text on cli
+- Use EPI2ME Labs-maintained version of pychopper
 
 ## [v0.1.2]
 ### Added

README.md

@@ -12,7 +12,7 @@ This workflow identifies RNA isoforms using either cDNA or direct RNA (dRNA)
 Oxford Nanopore reads.
 
 ### Preprocesing
-cDNA reads are initially preprocessed by [pychopper](https://github.com/nanoporetech/pychopper) 
+cDNA reads are initially preprocessed by [pychopper](https://github.com/epi2me-labs/pychopper) 
 for the identification of full-length reads, as well as trimming and orientation correction (This step is omitted for 
  direct RNA reads).
 

bin/report.py

@@ -498,7 +498,7 @@ def gff_compare_plots(report, gffcompare_outdirs: Path, sample_ids):
 
 
 def pychopper_plots(report, pychop_report):
-    """Make plots from pychopper.cdna_classifier.py.
+    """Make plots from pychopper output.
 
     :param report: aplanat WFReport
     :param pychop_report: path to pychopper stats file
@@ -507,7 +507,7 @@ def pychopper_plots(report, pychop_report):
     section.markdown('''
     ### Pychopper summary statisitcs
 
-    The following plots summarize the output of [cdna_classifier.py]
+    The following plots summarize [pychopper] output
     (https://github.com/nanoporetech/pychopper)
 
     * **Pr.found**: Reads with primers found in correct orientation at

docs/intro.md

@@ -4,7 +4,7 @@ This workflow identifies RNA isoforms using either cDNA or direct RNA (dRNA)
 Oxford Nanopore reads.
 
 ### Preprocesing
-cDNA reads are initially preprocessed by [pychopper](https://github.com/nanoporetech/pychopper) 
+cDNA reads are initially preprocessed by [pychopper](https://github.com/epi2me-labs/pychopper) 
 for the identification of full-length reads, as well as trimming and orientation correction (This step is omitted for 
  direct RNA reads).
 

environment.yaml

@@ -6,16 +6,16 @@ channels:
     - defaults
 dependencies:
     - python==3.8.*
-    - aplanat >=0.6.4
+    - aplanat>=0.6.4
     - epi2melabs
-    - minimap2 ==2.24
-    - samtools ==1.14
-    - bedtools ==2.30.0
-    - pychopper==2.5.0
+    - minimap2==2.24
+    - samtools==1.14
+    - bedtools==2.30.0
+    - pychopper>=2.7.0
     - pandas==1.3.5
     - gffread==0.12.7
     - gffcompare==0.11.2
-    - gffutils=0.10.1
+    - gffutils==0.10.1
     - seqkit==2.1.0
     - stringtie==2.1.1
     - curl

main.nf

@@ -74,7 +74,7 @@ process getParams {
 process preprocess_reads {
     /* 
     Concatenate reads from a sample directory.
-    Optionally classify, trim, and orient cDNA reads using cdna_classifier from pychopper
+    Optionally classify, trim, and orient cDNA reads using pychopper
     */
  
     label "isoforms"
@@ -87,13 +87,13 @@ process preprocess_reads {
          path '*.tsv',  emit: report
     script:
         """
-        cdna_classifier.py -t ${params.threads} ${params.pychopper_opts} ${input_reads} ${sample_id}_full_length_reads.fq
-        mv cdna_classifier_report.tsv ${sample_id}_cdna_classifier_report.tsv
-        generate_pychopper_stats.py --data ${sample_id}_cdna_classifier_report.tsv --output .
+        pychopper -t ${params.threads} ${params.pychopper_opts} ${input_reads} ${sample_id}_full_length_reads.fq
+        mv pychopper.tsv ${sample_id}_pychopper.tsv
+        generate_pychopper_stats.py --data ${sample_id}_pychopper.tsv --output .
 
         # Add sample id column
-        sed "1s/\$/\tsample_id/; 1 ! s/\$/\t${sample_id}/" ${sample_id}_cdna_classifier_report.tsv > tmp
-        mv tmp ${sample_id}_cdna_classifier_report.tsv
+        sed "1s/\$/\tsample_id/; 1 ! s/\$/\t${sample_id}/" ${sample_id}_pychopper.tsv > tmp
+        mv tmp ${sample_id}_pychopper.tsv
         """
 }
 

nextflow.config

@@ -23,7 +23,7 @@ params {
     sample = null
     sample_sheet = null
     sanitize_fastq = false
-    wfversion = "v0.1.2"
+    wfversion = "v0.1.3"
     aws_image_prefix = null
     aws_queue = null
     report_name = "report"

nextflow_schema.json

@@ -280,7 +280,7 @@
         },
         "wfversion": {
             "type": "string",
-            "default": "v0.1.2",
+            "default": "v0.1.3",
             "hidden": true
         },
         "monochrome_logs": {
@@ -295,7 +295,7 @@
         }
     },
     "docs": {
-        "intro": "## Introduction\n\nThis workflow identifies RNA isoforms using either cDNA or direct RNA (dRNA) \nOxford Nanopore reads.\n\n### Preprocesing\ncDNA reads are initially preprocessed by [pychopper](https://github.com/nanoporetech/pychopper) \nfor the identification of full-length reads, as well as trimming and orientation correction (This step is omitted for \n direct RNA reads).\n\n### Reference-aided approach\n* Full length reads are mapped to a supplied reference genome using [minimap2](https://github.com/lh3/minimap2)\n* Transcripts are assembled by [stringtie](http://ccb.jhu.edu/software/stringtie) \nin long read mode (with or without a guide reference annotation) to generate the GFF annotation.\n* The annotation generated by the pipeline is compared to the reference annotation. \nusing [gffcompare](http://ccb.jhu.edu/software/stringtie/gffcompare.shtml)\n\n### de novo-based approach (experimental!)\n* Sequence clusters are generated using [isONclust2](https://github.com/nanoporetech/isONclust2)\n  * If a reference genome is supplied, cluster quality metrics are determined by comparing    \n  with clusters generated from a minimap2 alignment.\n* A consensus sequence for each cluster is generated using [spoa](https://github.com/rvaser/spoa)\n* Three rounds of polishing using racon and minimap2 to give a final polished CDS for each gene.\n* Full-length reads are then mapped to these polished CDS.\n* Transcripts are assembled by stringtie as for the reference-based approach.\n* __Note__: This approach is currently not supported with direct RNA reads.\n\n### Workflow inputs\n- Directory containing cDNA/direct RNA reads. Or a directory containing subdirectories each with reads from different samples\n  (in fastq/fastq.gz format)\n- Reference genome in fasta format (required for reference-based assembly).\n- Optional reference annotation in GFF2/3 format.",
+        "intro": "## Introduction\n\nThis workflow identifies RNA isoforms using either cDNA or direct RNA (dRNA) \nOxford Nanopore reads.\n\n### Preprocesing\ncDNA reads are initially preprocessed by [pychopper](https://github.com/epi2me-labs/pychopper) \nfor the identification of full-length reads, as well as trimming and orientation correction (This step is omitted for \n direct RNA reads).\n\n### Reference-aided approach\n* Full length reads are mapped to a supplied reference genome using [minimap2](https://github.com/lh3/minimap2)\n* Transcripts are assembled by [stringtie](http://ccb.jhu.edu/software/stringtie) \nin long read mode (with or without a guide reference annotation) to generate the GFF annotation.\n* The annotation generated by the pipeline is compared to the reference annotation. \nusing [gffcompare](http://ccb.jhu.edu/software/stringtie/gffcompare.shtml)\n\n### de novo-based approach (experimental!)\n* Sequence clusters are generated using [isONclust2](https://github.com/nanoporetech/isONclust2)\n  * If a reference genome is supplied, cluster quality metrics are determined by comparing    \n  with clusters generated from a minimap2 alignment.\n* A consensus sequence for each cluster is generated using [spoa](https://github.com/rvaser/spoa)\n* Three rounds of polishing using racon and minimap2 to give a final polished CDS for each gene.\n* Full-length reads are then mapped to these polished CDS.\n* Transcripts are assembled by stringtie as for the reference-based approach.\n* __Note__: This approach is currently not supported with direct RNA reads.\n\n### Workflow inputs\n- Directory containing cDNA/direct RNA reads. Or a directory containing subdirectories each with reads from different samples\n  (in fastq/fastq.gz format)\n- Reference genome in fasta format (required for reference-based assembly).\n- Optional reference annotation in GFF2/3 format.",
         "links": "## Useful links\n\n* [nextflow](https://www.nextflow.io/)\n* [docker](https://www.docker.com/products/docker-desktop)\n* [Singularity](https://sylabs.io/singularity/)\n* [conda](https://docs.conda.io/en/latest/miniconda.html)\n* [racon](https://github.com/isovic/racon)\n* [spoa](https://github.com/rvaser/spoa)\n* [inONclust](https://github.com/ksahlin/isONclust)\n* [isONclust2](https://github.com/nanoporetech/isONclust2)"
     }
 }

reference_assembly.nf

@@ -2,7 +2,7 @@ process map_reads{
     /*
     Map reads to reference using minimap2.
     Filter reads by mapping quality.
-    Filter reads where length of poly(A) > max_poly_run at either ends of the read (defined by poly_context)
+    Filter internally-primed reads.
     */
     label "isoforms"
     cpus params.threads